The optimisation deep-draw clearance design for deep-draw dies

摘要

In this paper, the modelling of deep-drawing processing using neural networks is established. Therelationships between process parameter (material thickness, punch diameter, die-cavity diameterand materials-clearance ratio) and deep-drawing performance (the dimensional error of diameter andcylinder) are created, based on a neural network. A simulated annealing (SA) optimisation algorithmwith a performance index is then applied to the neural network to search for the optimal designparameters of the drawing-die. Experimental results have shown that deep-drawing performance canbe enhanced by using this approach.